Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    response

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mess
    -0.07
    KS
    -0.07
    getId
    -0.07
    docker
    -0.06
    Tên
    -0.06
     Geschichte
    -0.06
     билет
    -0.06
    not
    -0.06
     invers
    -0.06
     ht
    -0.06
    POSITIVE LOGITS
    大家分享
    0.07
    纮
    0.07
    usercontent
    0.07
    あ
    0.07
    舭
    0.07
    /renderer
    0.07
    侣
    0.07
     Misc
    0.07
    .panel
    0.07
    带回
    0.07
    Act Density 0.038%

    No Known Activations